Diagnostic value of artificial intelligence-assisted diagnostic system for pulmonary cancer based on CT images: A systematic review and meta-analysis of 4 771 patients_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

DONG Laidong ¹ ,  HUANG Guo ²

1. Outpatient Department, Qilu Hospital, Shandong University, Jinan, 250012, P.R.China;
2. School of Public Health, Fudan University, Shanghai, 200032, P.R.China;

Corresponding author：

HUANG Guo, Email: 2360191844@qq.com

Keywords：

Artificial intelligence-assisted diagnostic system; diagnostic value; pulmonary cancer; CT images; systematic review/meta-analysis

DOI：

10.7507/1007-4848.202012022

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To evaluate the diagnostic value of artificial intelligence (AI)-assisted diagnostic system for pulmonary cancer based on CT images.Methods Databases including PubMed, The Cochrane Library, EMbase, CNKI, WanFang Data and Chinese BioMedical Literature Database (CBM) were electronically searched to collect relevant studies on AI-assisted diagnostic system in the diagnosis of pulmonary cancer from 2010 to 2019. The eligible studies were selected according to inclusion and exclusion criteria, and the quality of included studies was assessed and the special information was identified. Then, meta-analysis was performed using RevMan 5.3, Stata 12.0 and SAS 9.4 softwares. The sensitivity, specificity, positive likelihood ratio, negative likelihood ratio and diagnostic odds ratio were pooled and the summary receiver operating characteristic (SROC) curve was drawn. Meta-regression analysis was used to explore the sources of heterogeneity.Results Totally 18 studies were included with 4 771 patients. Random effect model was used for the analysis due to the heterogeneity among studies. The results of meta-analysis showed that the pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnosis odds ratio and area under the SROC curve were 0.87 [95%CI (0.84, 0.90)], 0.89 [95%CI (0.84, 0.92)], 7.70 [95%CI (5.32, 11.15)], 0.14 [95%CI (0.11, 0.19)], 53.54 [95%CI (30.68, 93.42)] and 0.94 [95%CI (0.91, 0.95)], respectively.Conclusion AI-assisted diagnostic system based on CT images has high diagnostic value for pulmonary cancer, and thus it is worthy of clinical application. However, due to the limited quality and quantity of included studies, above results should be validated by more studies.

Citation： DONG Laidong, HUANG Guo. Diagnostic value of artificial intelligence-assisted diagnostic system for pulmonary cancer based on CT images: A systematic review and meta-analysis of 4 771 patients. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2021, 28(10): 1183-1191. doi: 10.7507/1007-4848.202012022 Copy

1.	Bray F, Ferlay J, Soerjomataram I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin, 2018, 68(6): 394-424.
2.	Amir GJ, Lehmann HP. After detection: The improved accuracy of lung cancer assessment using radiologic computer-aided diagnosis. Acad Radiol, 2016, 23(2): 186-191.
3.	孙惠昕. 人工智能在癌症筛查中的研究进展. 肿瘤预防与治疗, 2020, 33(10): 898-902.
4.	蓝美红, 高明明, 侯代伦. 超高分辨率CT靶扫描与CT靶重建在肺磨玻璃样结节定性诊断中的价值. 中国防痨杂志, 2018, 40(7): 702-706.
5.	王万勤, 刘斌, 周勇, 等. 良恶性肺结节多排CT征象分析. 安徽医药, 2018, 22(8): 1491-1496.
6.	赵呈华. 人工智能辅助诊断系统联合CT检查肺结节的诊断价值. 实用临床医药杂志, 2020, 24(19): 9-11.
7.	Schlattmann P, Schuetz GM, Dewey M. Wake up and smell the PRISMA, Cochrane, and QUADAS statements. Radiology, 2011, 261(1): 325-326.
8.	Bradley AP. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition, 1997, 30(7): 1145-1159.
9.	Sun T, Zhang R, Wang J, et al. Computer-aided diagnosis for early-stage lung cancer based on longitudinal and balanced data. PLoS One, 2013, 8(5): e63559.
10.	Wang J, Liu X, Dong D, et al. Prediction of malignant and benign of lung tumor using a quantitative radiomic method. Annu Int Conf IEEE Eng Med Biol Soc, 2016, 2016: 1272-1275.
11.	Dilger SKN. The use of surrounding lung parenchyma for the automated classification of pulmonary nodules. University of Iowa, 2013.
12.	Teramoto A, Tsujimoto M, Inoue T, et al. Automated classification of pulmonary nodules through a retrospective analysis of conventional CT and two-phase PET images in patients undergoing biopsy. Asia Ocean J Nucl Med Biol, 2019, 7(1): 29-37.
13.	张矗, 吴逸明, 吴拥军, 等. 人工神经网络技术在纤维支气管镜诊断肺癌中的应用. 郑州大学学报(医学版), 2010, 45(1): 113-115.
14.	邸晓东. 基于CT图像的孤立性肺结节诊断模型研究. 哈尔滨理工大学, 2010.
15.	刘宗才, 骆科进. MSCT LungCARE软件对孤立性肺结节的诊断价值. 贵州医药, 2010, 34(6): 539-542.
16.	徐力平, 张华杰, 吴逸明. 高斯隶属度函数模糊神经网络在肺癌诊断中的应用. 郑州大学学报(理学版), 2011, 43(1): 95-98.
17.	刘灿. 遗传算法优化模糊神经网络在肺癌诊断中的应用. 郑州大学, 2011.
18.	何俊诗, 梁鹏, 罗英华, 等. 基于神经网络的MSCT孤立肺小结节诊断模型的设计. 临床医学工程, 2012, 19(4): 497-499.
19.	王刚, 林森森, 姜新国, 等. 用于小细胞肺癌诊断的人工神经网络模型. 中国卫生统计, 2013, 30(2): 257-258.
20.	张极峰, 夏旭东, 李萍, 等. 计算机辅助诊断在孤立性肺结节CT诊断的应用. 医学影像学杂志, 2013, 23(9): 1386-1390.
21.	顾艳. 肺部孤立性结节与肿块常规形态学、CT灌注和计算机辅助诊断对比研究. 徐州医科大学, 2013.
22.	徐力平, 尚丹, 陈小玉. 模糊神经网络在肺癌CT诊断中的应用. 郑州大学学报(医学版), 2014, 49(2): 191-194.
23.	王克全, 张义兰, 邝双鑫. 肺癌CT诊断中应用模糊神经网络辅助诊断的效果探析. 深圳中西医结合杂志, 2015, 25(6): 70-71.
24.	张泽文, 张才擎, 王广丽, 等. 孤立性肺结节在HDCT的计算机辅助诊断. 医学影像学杂志, 2015, 25(6): 993-997.
25.	何霞霞, 张红升, 李迪, 等. 基于CT影像评分的人工神经网络模型对肺部良恶性病变的判别价值. 郑州大学学报(医学版), 2018, 53(6): 723-726.
26.	王霞. 基于数据挖掘技术的肺癌风险评估与诊断及组织分型系统研究. 郑州大学, 2019.
27.	印宏坤, 黄皓, 林强, 等. 拓展医疗人工智能的新疆界. 人工智能, 2018, 11(4): 88-96.
28.	杨尚文, 胡安宁, 徐亚运, 等. CT图像分辨率对人工智能肺结节辅助诊断系统诊断准确性的影响. 医学影像学杂志, 2020, 30(6): 965-968.
29.	高晨, 王世威, 许茂盛. 肺癌影像的人工智能研究. 中国中西医结合影像学杂志, 2020, 18(3): 219-223.
30.	动脉网. 联影智能AI入驻火神山、雷神山医院, 分析肺段以搜寻新冠病毒特征\|科技战疫. [2021-02-24]. https://mp.ofweek.com/medical/a945693520376.
31.	Huang XF, Lei Q, Xie T, et al. Deep transfer convolutional neural network and extreme learning machine for lung nodule diagnosis on CT images. Knowledge-Based Sys, 2020, 204(27): 106230.
32.	李幼平, 主编. 实用循证医学. 北京: 人民卫生出版社, 2018.
33.	陈长波. 肺部影像人工智能诊断系统对肺结节性质的诊断价值分析. 中国数字医学, 2020, 15(11): 40-42, 131.
34.	萧毅, 刘士远. 肺结节影像人工智能技术现状与思考. 肿瘤影像学, 2018, 27(4): 249-252.
35.	Zhang Y, Oikonomou A, Wong A, et al. Radiomics-based prognosis analysis for non-small cell lung cancer. Sci Rep, 2017, 7: 46349.
36.	Vogel L. Rise of medical AI poses new legal risks for doctors. CMAJ, 2019, 191(42): E1173-E1174.

1. Bray F, Ferlay J, Soerjomataram I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin, 2018, 68(6): 394-424.
2. Amir GJ, Lehmann HP. After detection: The improved accuracy of lung cancer assessment using radiologic computer-aided diagnosis. Acad Radiol, 2016, 23(2): 186-191.
3. 孙惠昕. 人工智能在癌症筛查中的研究进展. 肿瘤预防与治疗, 2020, 33(10): 898-902.
4. 蓝美红, 高明明, 侯代伦. 超高分辨率CT靶扫描与CT靶重建在肺磨玻璃样结节定性诊断中的价值. 中国防痨杂志, 2018, 40(7): 702-706.
5. 王万勤, 刘斌, 周勇, 等. 良恶性肺结节多排CT征象分析. 安徽医药, 2018, 22(8): 1491-1496.
6. 赵呈华. 人工智能辅助诊断系统联合CT检查肺结节的诊断价值. 实用临床医药杂志, 2020, 24(19): 9-11.
7. Schlattmann P, Schuetz GM, Dewey M. Wake up and smell the PRISMA, Cochrane, and QUADAS statements. Radiology, 2011, 261(1): 325-326.
8. Bradley AP. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition, 1997, 30(7): 1145-1159.
9. Sun T, Zhang R, Wang J, et al. Computer-aided diagnosis for early-stage lung cancer based on longitudinal and balanced data. PLoS One, 2013, 8(5): e63559.
10. Wang J, Liu X, Dong D, et al. Prediction of malignant and benign of lung tumor using a quantitative radiomic method. Annu Int Conf IEEE Eng Med Biol Soc, 2016, 2016: 1272-1275.
11. Dilger SKN. The use of surrounding lung parenchyma for the automated classification of pulmonary nodules. University of Iowa, 2013.
12. Teramoto A, Tsujimoto M, Inoue T, et al. Automated classification of pulmonary nodules through a retrospective analysis of conventional CT and two-phase PET images in patients undergoing biopsy. Asia Ocean J Nucl Med Biol, 2019, 7(1): 29-37.
13. 张矗, 吴逸明, 吴拥军, 等. 人工神经网络技术在纤维支气管镜诊断肺癌中的应用. 郑州大学学报(医学版), 2010, 45(1): 113-115.
14. 邸晓东. 基于CT图像的孤立性肺结节诊断模型研究. 哈尔滨理工大学, 2010.
15. 刘宗才, 骆科进. MSCT LungCARE软件对孤立性肺结节的诊断价值. 贵州医药, 2010, 34(6): 539-542.
16. 徐力平, 张华杰, 吴逸明. 高斯隶属度函数模糊神经网络在肺癌诊断中的应用. 郑州大学学报(理学版), 2011, 43(1): 95-98.
17. 刘灿. 遗传算法优化模糊神经网络在肺癌诊断中的应用. 郑州大学, 2011.
18. 何俊诗, 梁鹏, 罗英华, 等. 基于神经网络的MSCT孤立肺小结节诊断模型的设计. 临床医学工程, 2012, 19(4): 497-499.
19. 王刚, 林森森, 姜新国, 等. 用于小细胞肺癌诊断的人工神经网络模型. 中国卫生统计, 2013, 30(2): 257-258.
20. 张极峰, 夏旭东, 李萍, 等. 计算机辅助诊断在孤立性肺结节CT诊断的应用. 医学影像学杂志, 2013, 23(9): 1386-1390.
21. 顾艳. 肺部孤立性结节与肿块常规形态学、CT灌注和计算机辅助诊断对比研究. 徐州医科大学, 2013.
22. 徐力平, 尚丹, 陈小玉. 模糊神经网络在肺癌CT诊断中的应用. 郑州大学学报(医学版), 2014, 49(2): 191-194.
23. 王克全, 张义兰, 邝双鑫. 肺癌CT诊断中应用模糊神经网络辅助诊断的效果探析. 深圳中西医结合杂志, 2015, 25(6): 70-71.
24. 张泽文, 张才擎, 王广丽, 等. 孤立性肺结节在HDCT的计算机辅助诊断. 医学影像学杂志, 2015, 25(6): 993-997.
25. 何霞霞, 张红升, 李迪, 等. 基于CT影像评分的人工神经网络模型对肺部良恶性病变的判别价值. 郑州大学学报(医学版), 2018, 53(6): 723-726.
26. 王霞. 基于数据挖掘技术的肺癌风险评估与诊断及组织分型系统研究. 郑州大学, 2019.
27. 印宏坤, 黄皓, 林强, 等. 拓展医疗人工智能的新疆界. 人工智能, 2018, 11(4): 88-96.
28. 杨尚文, 胡安宁, 徐亚运, 等. CT图像分辨率对人工智能肺结节辅助诊断系统诊断准确性的影响. 医学影像学杂志, 2020, 30(6): 965-968.
29. 高晨, 王世威, 许茂盛. 肺癌影像的人工智能研究. 中国中西医结合影像学杂志, 2020, 18(3): 219-223.
30. 动脉网. 联影智能AI入驻火神山、雷神山医院, 分析肺段以搜寻新冠病毒特征|科技战疫. [2021-02-24]. https://mp.ofweek.com/medical/a945693520376.
31. Huang XF, Lei Q, Xie T, et al. Deep transfer convolutional neural network and extreme learning machine for lung nodule diagnosis on CT images. Knowledge-Based Sys, 2020, 204(27): 106230.
32. 李幼平, 主编. 实用循证医学. 北京: 人民卫生出版社, 2018.
33. 陈长波. 肺部影像人工智能诊断系统对肺结节性质的诊断价值分析. 中国数字医学, 2020, 15(11): 40-42, 131.
34. 萧毅, 刘士远. 肺结节影像人工智能技术现状与思考. 肿瘤影像学, 2018, 27(4): 249-252.
35. Zhang Y, Oikonomou A, Wong A, et al. Radiomics-based prognosis analysis for non-small cell lung cancer. Sci Rep, 2017, 7: 46349.
36. Vogel L. Rise of medical AI poses new legal risks for doctors. CMAJ, 2019, 191(42): E1173-E1174.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Diagnostic value of artificial intelligence-assisted diagnostic system for pulmonary cancer based on CT images: A systematic review and meta-analysis of 4 771 patients

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content